Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation

Published:2023-10-01 Issue: Volume:2 Page:16899-16910
ISSN:
Container-title:2023 IEEE/CVF International Conference on Computer Vision (ICCV)
language:
Short-container-title:

Author:

Ding Shuangrui¹,Zhao Peisen²,Zhang Xiaopeng²,Qian Rui³,Xiong Hongkai¹,Tian Qi²

Affiliation:

1. Shanghai Jiao Tong University

2. Huawei Cloud

3. The Chinese University of Hong Kong

Funder

National Natural Science Foundation of China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10376473/10376477/10376959.pdf?arnumber=10376959

Reference51 articles.

1. ViViT: A Video Vision Transformer

2. Is space-time attention all you need for video understanding?;Bertasius;ICML,2021

3. Token merging: Your vit but faster;Bolya

4. Space-time mixing attention for video transformer;Bulat;Advances in Neural Information Processing Systems,2021

5. Generative Semantic Segmentation

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Self-Supervised Representation Learning With Spatial-Temporal Consistency for Sign Language Recognition;IEEE Transactions on Image Processing;2024

2. Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP